INDEX

Explanations

expressions of exclusivity or limitation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(es

-0.15

ÐµÑĪ

-0.15

ÐºÐ¾ÑĤ

-0.14

SAME

-0.14

erp

-0.14

orgh

-0.14

oot

-0.13

ypes

-0.13

 å¸

-0.13

POSITIVE LOGITS

íģ¼

0.15

 Ð»Ð¸ÑĪÑĮ

0.15

 baÅŁÄ±na

0.14

Fans

0.14

Ð´ÑĸÐ»

0.14

phans

0.14

 Badge

0.14

DCF

0.14

idian

0.14

fans

0.14

Activations Density 0.063%

expressions of exclusivity or limitation

No Comments

No Known Activations